Decoding of finger movement using kinematic model classification and regression model switching

Elgharabawy, Ayman; Wahed, Manal Abdel

doi:10.1109/cibec.2016.7836126

Cited by 3 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To extract task-related spectral features, ECoG signal is either bandpass filtered (Liang and Bougrain, 2012; Chestek et al, 2013; Nakanishi et al, 2013) or converted into the frequency domain using non-parametric methods, such as Fourier transform (Chin et al, 2007; Miller et al, 2007; Blakely et al, 2009; Reddy et al, 2009; Ryun et al, 2014), multitaper methods (Ball et al, 2009; Kellis et al, 2012; Pistohl et al, 2012; Elgharabawy and Wahed, 2016), parametric techniques, such as autoregressive model estimation (Leuthardt et al, 2004; Schalk et al, 2007; Kubanek et al, 2009; Wang et al, 2012; Xie et al, 2015), and the maximum entropy approach (van Vugt et al, 2007; Collinger et al, 2014; Bundy et al, 2016; Gunduz et al, 2016). Spectral features can be also extracted with filter bank methods, such as Gabor filters (Liu et al, 2010; Elghrabawy and Wahed, 2012; Elgharabawy and Wahed, 2016; Wu et al, 2016). Ideally, neural signals should be processed in such a way that an optimal trade-off is reached between the temporal and spectral resolution.…”

Section: Decoding Algorithmsmentioning

confidence: 99%

“…Several filter selection algorithms utilize a wrapper-based approach, where features are scored using the learning algorithm that is then used for regression or classification (Gu et al, 2012). In this approach, the feature set is enhanced in consecutive steps, where features are added to the previous feature set to improve decoding accuracy estimated with cross-validation (Liang and Bougrain, 2012; Wang et al, 2012; Elgharabawy and Wahed, 2016; Li et al, 2017). When following these strategies, one should bear in mind that ECoG features assumed to be useful could be contaminated by noise that is accidentally correlated to the parameters being decoded.…”

Section: Decoding Algorithmsmentioning

confidence: 99%

“…This group of algorithms is versatile and allows constructing highly non-linear decision surfaces. Linear kernel is often used to prevent overfitting and ensure robustness (Yanagisawa et al, 2009, 2011; Ryun et al, 2014; Elgharabawy and Wahed, 2016). Additionally, radial basis functions can be employed (Wang et al, 2012).…”

Section: Decoding Algorithmsmentioning

confidence: 99%

“…Yanagisawa et al (2011) and Hotson et al (2016) used a hierarchical algorithm, where one model classified between rest and movement and detected movement onset and the second model classifies movement type. In several studies, switching between regression models was performed based on a classification algorithm (Flamary and Rakotomamonjy, 2012; Bundy et al, 2016; Elgharabawy and Wahed, 2016). Additionally, Chen et al developed an algorithm where the output of one model was used to weigh the output of the other model to improve prediction accuracy (Chen et al, 2014).…”

Section: Decoding Algorithmsmentioning

confidence: 99%

See 3 more Smart Citations

Decoding Movement From Electrocorticographic Activity: A Review

Volkova

Lebedev

Kaplan

et al. 2019

Front. Neuroinform.

View full text Add to dashboard Cite

Electrocorticography (ECoG) holds promise to provide efficient neuroprosthetic solutions for people suffering from neurological disabilities. This recording technique combines adequate temporal and spatial resolution with the lower risks of medical complications compared to the other invasive methods. ECoG is routinely used in clinical practice for preoperative cortical mapping in epileptic patients. During the last two decades, research utilizing ECoG has considerably grown, including the paradigms where behaviorally relevant information is extracted from ECoG activity with decoding algorithms of different complexity. Several research groups have advanced toward the development of assistive devices driven by brain-computer interfaces (BCIs) that decode motor commands from multichannel ECoG recordings. Here we review the evolution of this field and its recent tendencies, and discuss the potential areas for future development.

show abstract

Section: Decoding Algorithmsmentioning

confidence: 99%

Section: Decoding Algorithmsmentioning

confidence: 99%

Section: Decoding Algorithmsmentioning

confidence: 99%

Section: Decoding Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Decoding Movement From Electrocorticographic Activity: A Review

Volkova

Lebedev

Kaplan

et al. 2019

Front. Neuroinform.

View full text Add to dashboard Cite

show abstract

“…In particular, the problem of multi-finger movement trajectory reconstruction from ECoG recordings was studied. In most of the cases, hybrid models were employed by mixing classifier outputs to detect finger activations and continuous decoders to predict their respective movements [30][31][32].…”

Section: Introductionmentioning

confidence: 99%

An adaptive closed-loop ECoG decoder for long-term and stable bimanual control of an exoskeleton by a tetraplegic

et al. 2022

View full text Add to dashboard Cite

Objective. The article aims at addressing 2 challenges to step motor BCI out of laboratories: asynchronous control of complex bimanual effectors with large numbers of degrees of freedom, using chronic and safe recorders, and the decoding performance stability over time without frequent decoder recalibration. Approach. Closed-loop adaptive/incremental decoder training is one strategy to create a model stable over time. Adaptive decoders update their parameters with new incoming data, optimizing the model parameters in real time. It allows cross-session training with multiple recording conditions during closed loop BCI experiments. In the article, an adaptive tensor-based Recursive Exponentially Weighted Markov-Switching multi-Linear Model (REW-MSLM) decoder is proposed. REW-MSLM uses a Mixture of Expert (ME) architecture, mixing or switching independent decoders (experts) according to the probability estimated by a “gating” model. A Hidden Markov model approach is employed as gating model to improve the decoding robustness and to provide strong idle state support. The ME architecture fits the multi-limb paradigm associating an expert to a particular limb or action. Main results. Asynchronous control of an exoskeleton by a tetraplegic patient using a chronically implanted epidural electrocorticography (EpiCoG) recorder is reported. The stable over a period of 6 months (without decoder recalibration) 8-dimensional alternative bimanual control of the exoskeleton and its virtual avatar is demonstrated. Significance. Based on the long-term (>36 months) chronic bilateral epidural ECoG recordings in a tetraplegic (ClinicalTrials.gov, NCT02550522), we addressed the poorly explored field of asynchronous bimanual BCI. The new decoder was designed to meet to several challenges: the high-dimensional control of a complex effector in experiments closer to real-world behaviour (point-to-point pursuit versus conventional center-out tasks), with the ability of the BCI system to act as a stand-alone device switching between idle and control states, and a stable performance over a long period of time without decoder recalibration.

show abstract

Decoding ECoG Signal with Deep Learning Model Based on LSTM

Yang

Liu

et al. 2018

TENCON 2018 - 2018 IEEE Region 10 Conference

View full text Add to dashboard Cite

Decoding of finger movement using kinematic model classification and regression model switching

Cited by 3 publications

References 21 publications

Decoding Movement From Electrocorticographic Activity: A Review

Decoding Movement From Electrocorticographic Activity: A Review

An adaptive closed-loop ECoG decoder for long-term and stable bimanual control of an exoskeleton by a tetraplegic

Decoding ECoG Signal with Deep Learning Model Based on LSTM

Contact Info

Product

Resources

About